{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/retry-with-exponential-backoff","entry":"retry_with_exponential_backoff","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":11,"n_papers_ran":6,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":12,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"unverified":5},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2609.12584","paper":"/paper/arxiv-2609-12584","title":"Clustering-Based Balanced Sampling and Allocation with Data Parallelism for High-Performance Fine-Tuning","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"kaist-dmlab/CluSTER","path":"src/CluSTER/utils.py","file_url":"https://github.com/kaist-dmlab/CluSTER/blob/HEAD/src/CluSTER/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"242afd6eeaf6458a","mcp_get_code":{"code_sha256":"242afd6eeaf6458a"}},{"arxiv_id":"2608.30730","paper":"/paper/arxiv-2608-30730","title":"E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"QwenLM/E-CommerceBench","path":"agent/llm_client.py","file_url":"https://github.com/QwenLM/E-CommerceBench/blob/HEAD/agent/llm_client.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1c08409b73510f71","mcp_get_code":{"code_sha256":"1c08409b73510f71"}},{"arxiv_id":"2505.18079","paper":"/paper/deep-video-discovery-agentic-search-with-tool","title":"Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding","date":"2025-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/DeepVideoDiscovery","path":"dvd/utils.py","file_url":"https://github.com/microsoft/DeepVideoDiscovery/blob/HEAD/dvd/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d7378512b752bfef","mcp_get_code":{"code_sha256":"d7378512b752bfef"}},{"arxiv_id":"2502.20073","paper":"/paper/collab-overcooked-benchmarking-and-evaluating","title":"Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yusaemeow/collab-overcooked","path":"src/collab/utils.py","file_url":"https://github.com/yusaemeow/collab-overcooked/blob/HEAD/src/collab/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e164796d18f375ac","mcp_get_code":{"code_sha256":"e164796d18f375ac"}},{"arxiv_id":"2410.19609","paper":"/paper/openwebvoyager-building-multimodal-web-agents","title":"OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization","date":"2024-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minorjerry/openwebvoyager","path":"WebVoyager/utils_localhost.py","file_url":"https://github.com/minorjerry/openwebvoyager/blob/HEAD/WebVoyager/utils_localhost.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b84fb0440ded170d","mcp_get_code":{"code_sha256":"b84fb0440ded170d"}},{"arxiv_id":"2410.13860","paper":"/paper/vlm-grounder-a-vlm-agent-for-zero-shot-3d","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openrobotlab/vlm-grounder","path":"vlm_grounder/utils/my_openai.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/my_openai.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e422c96b99ba09d6","mcp_get_code":{"code_sha256":"e422c96b99ba09d6"}},{"arxiv_id":"2410.13860","paper":"/paper/vlm-grounder-a-vlm-agent-for-zero-shot-3d","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openrobotlab/vlm-grounder","path":"vlm_grounder/utils/online_detector.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/online_detector.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"faf7e416de9cc8d4","mcp_get_code":{"code_sha256":"faf7e416de9cc8d4"}},{"arxiv_id":"2407.06576","paper":"/paper/virtual-personas-for-language-models-via-an","title":"Virtual Personas for Language Models via an Anthology of Backstories","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cannylab/anthology","path":"anthology/lm_inference/backoff.py","file_url":"https://github.com/cannylab/anthology/blob/HEAD/anthology/lm_inference/backoff.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"052a7adf33f0375f","mcp_get_code":{"code_sha256":"052a7adf33f0375f"}},{"arxiv_id":"2406.11149","paper":"/paper/goldcoin-grounding-large-language-models-in","title":"GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkust-knowcomp/goldcoin","path":"models/chatgpt.py","file_url":"https://github.com/hkust-knowcomp/goldcoin/blob/HEAD/models/chatgpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d6c933ebecaf2f0b","mcp_get_code":{"code_sha256":"d6c933ebecaf2f0b"}},{"arxiv_id":"2405.20363","paper":"/paper/llmgeo-benchmarking-large-language-models-on","title":"LLMGeo: Benchmarking Large Language Models on Image Geolocation In-the-wild","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yeyimilk/llmgeo","path":"src/chatgpt.py","file_url":"https://github.com/yeyimilk/llmgeo/blob/HEAD/src/chatgpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5277902dc67fdd10","mcp_get_code":{"code_sha256":"5277902dc67fdd10"}},{"arxiv_id":"2403.06833","paper":"/paper/can-llms-separate-instructions-from-data-and","title":"Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"egozverev/Shold-It-Be-Executed-Or-Processed","path":"openai_utils.py","file_url":"https://github.com/egozverev/Shold-It-Be-Executed-Or-Processed/blob/HEAD/openai_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a4770293aaa8cd1b","mcp_get_code":{"code_sha256":"a4770293aaa8cd1b"}},{"arxiv_id":"2310.03368","paper":"/paper/evaluating-hallucinations-in-chinese-large","title":"Evaluating Hallucinations in Chinese Large Language Models","date":"2023-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiami2019/halluqa","path":"calculate_metrics.py","file_url":"https://github.com/xiami2019/halluqa/blob/HEAD/calculate_metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c94f95f0f7f68a7a","mcp_get_code":{"code_sha256":"c94f95f0f7f68a7a"}}]}